paper-with-me

Papers

Towards Principled Representation Learning from Videos for Reinforcement Learning

2024-03-20 · Dipendra Misra, Akanksha Saran, Tengyang Xie, Alex Lamb, John Langford

We study pre-training representations for decision-making using video data, which is abundantly available for tasks such as game agents and software testing. Even though significant empirical advances have been made on this problem, a theoretical understanding remains absent. We initiate the theoretical investigation into principled approaches for representation learning and focus on learning the latent state representations of the underlying MDP using video data. We study two types of settings: one where there is iid noise in the observation, and a more challenging setting where there is also the presence of exogenous noise, which is non-iid noise that is temporally correlated, such as the motion of people or cars in the background. We study three commonly used approaches: autoencoding, temporal contrastive learning, and forward modeling. We prove upper bounds for temporal contrastive learning and forward modeling in the presence of only iid noise. We show that these approaches can learn the latent state and use it to do efficient downstream RL with polynomial sample complexity. When exogenous noise is also present, we establish a lower bound result showing that the sample complexity of learning from video data can be exponentially worse than learning from action-labeled trajectory data. This partially explains why reinforcement learning with video pre-training is hard. We evaluate these representational learning methods in two visual domains, yielding results that are consistent with our theoretical findings.

📄 PDF Abstract BibTeX arXiv:2403.13765

Code (1)

microsoft/intrepid 공식 구현 pytorch

Tasks

Contrastive Learningreinforcement-learningReinforcement LearningRepresentation Learningsoftware testing

Methods 이 논문이 사용한 방법론

Focus 설명 없음
Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model

2019-07-01 · NeurIPS 2020 12 · Alex X. Lee, Anusha Nagabandi, Pieter Abbeel, Sergey Levine

Deep reinforcement learning (RL) algorithms can use high-capacity deep networks to learn directly from image observations. However, these high-dimensional observation spaces present a number of challenges in practice, si…

continuous-controlContinuous ControlDeep Reinforcement Learningreinforcement-learning+3

Learning Task-Agnostic Skill Bases to Uncover Motor Primitives in Animal Behaviors

2025-06-18 · Jiyi Wang, Jingyang Ke, Bo Dai, Anqi Wu

Animals flexibly recombine a finite set of core motor primitives to meet diverse task demands, but existing behavior-segmentation methods oversimplify this process by imposing discrete syllables under restrictive generat…

Imitation LearningRepresentation Learning

Pre-trained Visual Dynamics Representations for Efficient Policy Learning

2024-11-05 · Hao Luo, Bohan Zhou, Zongqing Lu

Pre-training for Reinforcement Learning (RL) with purely video data is a valuable yet challenging problem. Although in-the-wild videos are readily available and inhere a vast amount of prior world knowledge, the absence …

Reinforcement Learning (RL)Video PredictionWorld Knowledge

Towards Learning Controllable Representations of Physical Systems

2020-11-16 · Kevin Haninger, Raul Vicente Garcia, Joerg Krueger

Learned representations of dynamical systems reduce dimensionality, potentially supporting downstream reinforcement learning (RL). However, no established methods predict a representation's suitability for control and ev…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Reinforcement Learning, Bit by Bit

2021-03-06 · Xiuyuan Lu, Benjamin Van Roy, Vikranth Dwaracherla, Morteza Ibrahimi 외

Reinforcement learning agents have demonstrated remarkable achievements in simulated environments. Data efficiency poses an impediment to carrying this success over to real environments. The design of data-efficient agen…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)